Changeset 16026 for branches/2886_SymRegGrammarEnumeration/HeuristicLab.Algorithms.DataAnalysis.SymRegGrammarEnumeration/Analysis

Timestamp:

07/27/18 19:28:18 (6 years ago)

Author:

bburlacu

Message:

#2886:

• replace functionally-overlapping classes Production and SymbolString with a single class SymbolList
• refactor methods from Grammar class as methods and properties of SymbolList
• add parameter for the number of constant optimization iterations
• refactor code

Location:

branches/2886_SymRegGrammarEnumeration/HeuristicLab.Algorithms.DataAnalysis.SymRegGrammarEnumeration/Analysis

Files:

• RSquaredEvaluator.cs (modified) (7 diffs)
• SearchGraphVisualizer.cs (modified) (1 diff)
• SentenceLogger.cs (modified) (2 diffs)

branches/2886_SymRegGrammarEnumeration/HeuristicLab.Algorithms.DataAnalysis.SymRegGrammarEnumeration/Analysis/RSquaredEvaluator.cs

@@ -1 +1 @@
 using System;
 using System.Diagnostics;
-using HeuristicLab.Algorithms.DataAnalysis.SymRegGrammarEnumeration.GrammarEnumeration;
 using HeuristicLab.Analysis;
 using HeuristicLab.Common;
@@ -51 +50 @@
     private void AlgorithmOnDistinctSentenceGenerated(object sender, PhraseAddedEventArgs phraseAddedEventArgs) {
       GrammarEnumerationAlgorithm algorithm = (GrammarEnumerationAlgorithm)sender;
-      EvaluateSentence(algorithm, phraseAddedEventArgs.NewPhrase, algorithm.OptimizeConstants);
+      EvaluateSentence(algorithm, phraseAddedEventArgs.NewPhrase, algorithm.OptimizeConstants, algorithm.ConstantOptimizationIterations);
     }
 
@@ -69 +68 @@
     }
 
-    private void EvaluateSentence(GrammarEnumerationAlgorithm algorithm, SymbolString symbolString, bool optimizeConstants) {
+    private void EvaluateSentence(GrammarEnumerationAlgorithm algorithm, SymbolList sentence, bool optimizeConstants, int maxIterations) {
       var results = algorithm.Results;
       var grammar = algorithm.Grammar;
       var problemData = algorithm.Problem.ProblemData;
 
-      SymbolicExpressionTree tree = algorithm.Grammar.ParseSymbolicExpressionTree(symbolString);
+      SymbolicExpressionTree tree = algorithm.Grammar.ParseSymbolicExpressionTree(sentence);
       Debug.Assert(SymbolicRegressionConstantOptimizationEvaluator.CanOptimizeConstants(tree));
 
-      double r2 = Evaluate(problemData, tree, optimizeConstants);
+      double r2 = Evaluate(problemData, tree, optimizeConstants, maxIterations);
       double bestR2 = results.ContainsKey(BestTrainingQualityResultName) ? GetValue<double>(results[BestTrainingQualityResultName].Value) : 0.0;
       if (r2 < bestR2)
@@ -83 +82 @@
 
       var bestComplexity = results.ContainsKey(BestComplexityResultName) ? GetValue<int>(results[BestComplexityResultName].Value) : int.MaxValue;
-      var complexity = grammar.GetComplexity(symbolString);
+      var complexity = sentence.Complexity;
 
       if (algorithm.BestTrainingSentence == null || r2 > bestR2 || (r2.IsAlmost(bestR2) && complexity < bestComplexity)) {
-        algorithm.BestTrainingSentence = symbolString;
+        algorithm.BestTrainingSentence = sentence;
 
         var model = new SymbolicRegressionModel(problemData.TargetVariable, tree, expressionTreeLinearInterpreter);
@@ -110 +109 @@
         dt = (DataTable)results[BestSolutions].Value;
         dt.Rows["Quality"].Values.Add(r2);
-        dt.Rows["Relative Length"].Values.Add((double)symbolString.Count() / algorithm.MaxSentenceLength);
+        dt.Rows["Relative Length"].Values.Add((double)sentence.Count);
         dt.Rows["Complexity"].Values.Add(complexity);
         dt.Rows["Timestamp"].Values.Add(algorithm.ExecutionTime.TotalMilliseconds / 1000d);
@@ -116 +115 @@
     }
 
-    public static double Evaluate(IRegressionProblemData problemData, SymbolicExpressionTree tree, bool optimizeConstants = true) {
+    public static double Evaluate(IRegressionProblemData problemData, SymbolicExpressionTree tree, bool optimizeConstants = true, int maxIterations = 10) {
       double r2;
 
@@ -127 +126 @@
           problemData.TrainingIndices,
           applyLinearScaling: true,
-          maxIterations: 10,
+          maxIterations: maxIterations,
           updateVariableWeights: false,
           updateConstantsInTree: true);

branches/2886_SymRegGrammarEnumeration/HeuristicLab.Algorithms.DataAnalysis.SymRegGrammarEnumeration/Analysis/SearchGraphVisualizer.cs

@@ -55 +55 @@
       try {
         var alg = (GrammarEnumerationAlgorithm)sender;
-        var phrase0 = new SymbolString(new[] { alg.Grammar.StartSymbol });
+        var phrase0 = new SymbolList(new[] { alg.Grammar.StartSymbol });
         var phrase0Hash = alg.Grammar.Hasher.CalcHashCode(phrase0);
 

branches/2886_SymRegGrammarEnumeration/HeuristicLab.Algorithms.DataAnalysis.SymRegGrammarEnumeration/Analysis/SentenceLogger.cs

@@ -89 +89 @@
       distinctSentencesFileTrace.WriteLine(ToCsvLine(
         ((uint)phraseAddedEventArgs.NewHash).ToString("D10"),
-        phraseAddedEventArgs.NewPhrase.Count().ToString("D3"),
+        phraseAddedEventArgs.NewPhrase.Count.ToString("D3"),
         //phraseAddedEventArgs.NewPhrase.ToString(),
         ((GrammarEnumerationAlgorithm)sender).Grammar.ToInfixString(phraseAddedEventArgs.NewPhrase)));
@@ -99 +99 @@
       allSentencesFileTrace.WriteLine(ToCsvLine(
         ((uint)phraseAddedEventArgs.NewHash).ToString("D10"),
-        phraseAddedEventArgs.NewPhrase.Count().ToString("D3"),
+        phraseAddedEventArgs.NewPhrase.Count.ToString("D3"),
         //phraseAddedEventArgs.NewPhrase.ToString(),
         ((GrammarEnumerationAlgorithm)sender).Grammar.ToInfixString(phraseAddedEventArgs.NewPhrase)));